Related papers: Test-Time Training with Masked Autoencoders
Time-series anomaly detection deals with the problem of detecting anomalous timesteps by learning normality from the sequence of observations. However, the concept of normality evolves over time, leading to a "new normal problem", where the…
Data samples generated by several real world processes are dynamic in nature \textit{i.e.}, their characteristics vary with time. Thus it is not possible to train and tackle all possible distributional shifts between training and inference,…
Masked autoencoders have become popular training paradigms for self-supervised visual representation learning. These models randomly mask a portion of the input and reconstruct the masked portion according to the target representations. In…
We analyze the training of a two-layer autoencoder used to parameterize a flow-based generative model for sampling from a high-dimensional Gaussian mixture. Previous work shows that the phase where the relative probability between the modes…
This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core…
Cross-language learning allows us to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-level alignment of sentences from parallel corpora. In this…
We present a novel approach for test-time adaptation via online self-training, consisting of two components. First, we introduce a statistical framework that detects distribution shifts in the classifier's entropy values obtained on a…
Large-scale self-supervised pre-training Transformer architecture have significantly boosted the performance for various tasks in natural language processing (NLP) and computer vision (CV). However, there is a lack of researches on…
Test-Time Adaptation (TTA) methods improve the robustness of deep neural networks to domain shift on a variety of tasks such as image classification or segmentation. This work explores adapting segmentation models to a single unlabelled…
Multi-modal data-sets are ubiquitous in modern applications, and multi-modal Variational Autoencoders are a popular family of models that aim to learn a joint representation of the different modalities. However, existing approaches suffer…
Common domain shift problem formulations consider the integration of multiple source domains, or the target domain during training. Regarding the generalization of machine learning models between different car interiors, we formulate the…
Deep neural networks often exhibit poor performance on data that is unlikely under the train-time data distribution, for instance data affected by corruptions. Previous works demonstrate that test-time adaptation to data shift, for instance…
Feedforward neural networks are widely used as universal predictive models to fit data distribution. Common gradient-based learning, however, suffers from many drawbacks making the training process ineffective and time-consuming.…
Test-time adaptation enables a trained model to adjust to a new domain during inference, making it particularly valuable in clinical settings where such on-the-fly adaptation is required. However, existing techniques depend on large target…
In this paper we delve into the properties of transformers, attained through self-supervision, in the point cloud domain. Specifically, we evaluate the effectiveness of Masked Autoencoding as a pretraining scheme, and explore Momentum…
Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated distribution shifts in test data. However, test-time adaptation of video action recognition…
We consider the problem of improving the human instance segmentation mask quality for a given test image using keypoints estimation. We compare two alternative approaches. The first approach is a test-time adaptation (TTA) method, where we…
Class distribution plays an important role in learning deep classifiers. When the proportion of each class in the test set differs from the training set, the performance of classification nets usually degrades. Such a label distribution…
Masked Autoencoder (MAE) is a self-supervised approach for representation learning, widely applicable to a variety of downstream tasks in computer vision. In spite of its success, it is still not fully uncovered what and how MAE exactly…
Trajectory prediction is a challenging problem that requires considering interactions among multiple actors and the surrounding environment. While data-driven approaches have been used to address this complex problem, they suffer from…